文献类型：期刊文献

英文题名：A modified extreme learning machine with sigmoidal activation functions

作者：Chen, Zhixiang X.[1];Zhu, Houying Y.[2];Wang, Yuguang G.[2]

机构：[1]Shaoxing Univ, Dept Math, Shaoxing 312000, Zhejiang, Peoples R China;[2]China Jiliang Univ, Dept Informat & Math Sci, Hangzhou 310018, Zhejiang, Peoples R China

年份：2013

卷号：22

期号：3-4

起止页码：541

外文期刊名：NEURAL COMPUTING & APPLICATIONS

收录：SCI-EXPANDED(收录号：WOS:000314844300013)、、EI(收录号：20130816047196)、Scopus(收录号：2-s2.0-84874020734)、WOS

基金：We would thank Feilong Cao for his suggestions on this paper. The support of the National Natural Science Foundation of China (Nos. 90818020, 10871226, 61179041) is gratefully acknowledged.

语种：英文

外文关键词：Feedforward neural networks; Extreme learning machine; Moore-Penrose generalized inverse

外文摘要：This paper proposes a modified ELM algorithm that properly selects the input weights and biases before training the output weights of single-hidden layer feedforward neural networks with sigmoidal activation function and proves mathematically the hidden layer output matrix maintains full column rank. The modified ELM avoids the randomness compared with the ELM. The experimental results of both regression and classification problems show good performance of the modified ELM algorithm.